Authors
Andrea Zaliani, Arianna Pisati, Agnese Pozzi, Alessandro Pedretti, Giulio Vistoli
Published in
Journal of medicinal chemistry. Volume 69. Issue 21. Pages 25228-25235. Nov 12, 2026.
Abstract
The proprietary nature of AI/ML tools in drug discovery limits access to advanced virtual screening methodologies. To address this, we present an open-source, automated pipeline for large-scale Quantitative Structure-Activity Relationship (QSAR) modeling utilizing ChEMBL. Our batch processing system constructed 2263 predictive models across multiple protein targets, applying both regression and classification strategies with strict quality control thresholds. The pipeline integrates ErG and RDKit descriptor families, employs Random Forest and XGBoost algorithms with Optuna-based hyperparameter optimization, and handles class imbalances using SMOTE. Models are saved only when achieving R2 ≥ 0.7 for regression or MCC ≥ 0.55 for classification. Data is stratified by assay and measurement types to maintain biological relevance. Additionally, we feature an interactive EDA visualization tool with ErG heatmaps and external validation via the DELTA database. This work democratizes industrial-grade QSAR infrastructure, empowering the research community to reproduce and extend computational workflows.
PMID:
43018628
Bibliographic data and abstract were imported from PubMed on 12 Nov 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 5
- Comments 0